Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ứa
    -0.07
    개월
    -0.07
    YRO
    -0.06
    泛
    -0.06
    欢
    -0.06
    潮
    -0.06
    ối
    -0.06
    πτυ
    -0.06
     openness
    -0.06
    -density
    -0.06
    POSITIVE LOGITS
    _tensors
    0.07
    яем
    0.07
    _bed
    0.06
    _when
    0.06
     reasoned
    0.06
    检测
    0.06
     Incorporated
    0.06
     suites
    0.06
    _METHOD
    0.06
     stagn
    0.06
    Act Density 0.021%

    No Known Activations